K-prototypes 군집분석 알고리즘을 적용한 코로나19 팬데믹 전후의 국내 여행행태 비교 연구

Abstract

The purpose of this study was to apply the k-prototypes algorithm, capable of handling both continuous and categorical variables, to gain insights into the changes in travel patterns between the pre- and peri-COVID-19 pandemic periods. For the empirical analysis, data from the National Travel Survey conducted from 2018 to 2021 were extracted, specifically focusing on respondents in Seoul, Gyeonggi, and Incheon (n=21,161). A comparison between the pre- and peri-COVID-19 pandemic periods revealed significant changes, including an increase in visits to short-distance destinations, a decrease in the number of travel companions and travel spending, an increased reliance on personal experiences as a source of travel information, and a decrease in travel among the elderly population. Furthermore, a comparative analysis of travel pattern clusters demonstrated that six travel pattern clusters, namely ‘long-distance travel group’, ‘high-frequency travel group’, ‘friend/couple group’, ‘travel group with children’, ‘high-spending group’, and ‘group traveler’, remained consistent during the peri-COVID-19 period, except for the ‘group traveler’ cluster. The implications of the research findings are discussed, along with suggestions for future research directions.